Applied GAI in Security

Sign in Subscribe

News

Last Week in GAI Security Research - 06/10/24

Last Week in GAI Security Research - 06/10/24

Highlights from Last Week * 💉Exfiltration of personal information from ChatGPT via prompt injection * 🦥 Are you still on track!? Catching LLM Task Drift with Activations * 🕵 Ranking Manipulation for Conversational Search Engines * 💔 BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models * 🎼 Transforming Computer Security and Public Trust Through the Exploration

Last Week in GAI Security Research - 05/20/24

Last Week in GAI Security Research - 05/20/24

Discover cutting-edge advancements in LLMs for steganalysis, chip design security, DDoS detection, cyber news classification, and SMS spam detection.

Last Week in GAI Security Research - 05/06/24

Last Week in GAI Security Research - 05/06/24

Explore cutting-edge research on malware detection, backdoor attacks, and code deobfuscation in LLMs

Last Week in GAI Security Research - 04/29/24

Last Week in GAI Security Research - 04/29/24

Explore AI security with insights on jailbreaking LLMs, image generation, phishing detection, trojan triggers, and API attacks. Discover advanced defense techniques in AI cybersecurity.

Last Week in GAI Security Research - 04/22/24

Last Week in GAI Security Research - 04/22/24

Unlock cutting-edge AI & cybersecurity insights: From robust LLM defenses to tackling AI threats, stay ahead in the tech game with our latest analyses.

Last Week in GAI Security Research - 04/15/24

Last Week in GAI Security Research - 04/15/24

Balancing AI safety with functionality, highlighting attack effectiveness, exposing language vulnerabilities, innovating content moderation, and exploring security nuances.

Last Week in GAI Security Research - 04/08/24

Last Week in GAI Security Research - 04/08/24

Delve into cutting-edge AI defenses and vulnerabilities: From robust strategies against sophisticated attacks to the exploration of LLM jailbreak phenomena.